Transformer Condition Assessment Based On Cloudmodel And Gray-fuzzy Comprehensive Evaluation

Power transformer is one of the most important electrical equipment in power system,and its operating condition is directly related to the safety and reliability of power system.With the increase of power grid capacity and scale,the influence of transformer fault is becoming more and more serious.At present,some transformers have been operating for more than 20 years in China,and these transformers are faced with more serious problems.such as insulation aging,partial discharge,failure of parts and so on.Therefore,it is of practical significance to prevent and reduce the occurrence of transformer faults by conducting in-depth research on transformer condition assessment.In view of the gray,fuzziness and randomness of the transformer condition assessment indicators,this paper combines the cloud model with the gray-fuzzy comprehensive evaluation to assess the condition of the transformer.Firstly,based on the relevant test procedures,literature,the dissolved gas in oil,electrical test,and insulating oil test are selected as the secondary-level evaluation indicators.Under each secondary-level indicator,select its own first-level assessment indicators,establish a hierarchical evaluation indicators system.Then,the fuzzy part of the weight set of first-level assessment indicators is calculated based on the optimal weight,its gray part of the weight set is calculated based on the redundancy degree of information and the experiences of experts.the fuzzy part of the weight set of secondary-level assessment indicators is calculated based on the fuzzy analytic hierarchy process,its gray part of the weight set is calculated based on the redundancy degree of information and the experiences of experts.Determine the assessment indicators weight set.The cloud model is used to describe the fuzzy subordinating relationship between the assessment indicators and the condition hierarchy.The point gray scale is used to describe the unreliability of the fuzzy relationship.a gray fuzzy judgement matrix is established.The judging formula is used to calculate the judging result.The judging result uses the inner product method and the principle of maximum subordinating degree to finally determine the transformer condition level.Through the verification of two examples and the analysis of application effects,it shows that the model can effectively assess the true running condition of the transformer,and the model has a higher recognition accuracy.